{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V6DSV7JZCOF6ESW3BMXHJATCUQ","short_pith_number":"pith:V6DSV7JZ","schema_version":"1.0","canonical_sha256":"af872afd39138be24adb0b2e748262a4063eac14ea257403dbf8d0acc4d1709d","source":{"kind":"arxiv","id":"2505.10507","version":2},"attestation_state":"computed","paper":{"title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benedikt Ebing, Goran Glava\\v{s}","submitted_at":"2025-05-15T17:10:50Z","abstract_excerpt":"Translation-based strategies for cross-lingual transfer XLT such as translate-train -- training on noisy target language data translated from the source language -- and translate-test -- evaluating on noisy source language data translated from the target language -- are competitive XLT baselines. In XLT for token classification tasks, however, these strategies include label projection, the challenging step of mapping the labels from each token in the original sentence to its counterpart(s) in the translation. Although word aligners (WAs) are commonly used for label projection, the low-level de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.10507","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T17:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"00248019d8dbdff69ef64808867a1011cfbb57378fb4a18adc48592b3331550d","abstract_canon_sha256":"47e96cb51b93ea62cbf13cf199f5759b38d9f777741c407e50eab4f170ecbc8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:36.762922Z","signature_b64":"/B+Hif/2Qcr7LC32a1WJW0tKNHjpNlX/7zbaOMCW+ZFy/wJpFj1lPnJ264wYug7CB28el/VElXoHJgjDk3LgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af872afd39138be24adb0b2e748262a4063eac14ea257403dbf8d0acc4d1709d","last_reissued_at":"2026-07-05T11:50:36.762426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:36.762426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benedikt Ebing, Goran Glava\\v{s}","submitted_at":"2025-05-15T17:10:50Z","abstract_excerpt":"Translation-based strategies for cross-lingual transfer XLT such as translate-train -- training on noisy target language data translated from the source language -- and translate-test -- evaluating on noisy source language data translated from the target language -- are competitive XLT baselines. In XLT for token classification tasks, however, these strategies include label projection, the challenging step of mapping the labels from each token in the original sentence to its counterpart(s) in the translation. Although word aligners (WAs) are commonly used for label projection, the low-level de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10507","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.10507/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.10507","created_at":"2026-07-05T11:50:36.762482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10507v2","created_at":"2026-07-05T11:50:36.762482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10507","created_at":"2026-07-05T11:50:36.762482+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6DSV7JZCOF6","created_at":"2026-07-05T11:50:36.762482+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6DSV7JZCOF6ESW3","created_at":"2026-07-05T11:50:36.762482+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6DSV7JZ","created_at":"2026-07-05T11:50:36.762482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ","json":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ.json","graph_json":"https://pith.science/api/pith-number/V6DSV7JZCOF6ESW3BMXHJATCUQ/graph.json","events_json":"https://pith.science/api/pith-number/V6DSV7JZCOF6ESW3BMXHJATCUQ/events.json","paper":"https://pith.science/paper/V6DSV7JZ"},"agent_actions":{"view_html":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ","download_json":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ.json","view_paper":"https://pith.science/paper/V6DSV7JZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10507&json=true","fetch_graph":"https://pith.science/api/pith-number/V6DSV7JZCOF6ESW3BMXHJATCUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/V6DSV7JZCOF6ESW3BMXHJATCUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ/action/storage_attestation","attest_author":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ/action/author_attestation","sign_citation":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ/action/citation_signature","submit_replication":"https://pith.science/pith/V6DSV7JZCOF6ESW3BMXHJATCUQ/action/replication_record"}},"created_at":"2026-07-05T11:50:36.762482+00:00","updated_at":"2026-07-05T11:50:36.762482+00:00"}